Free-hand 3D reconstruction and tumor segmentation of Laparoscopic Ultrasounds for pancreatic MIS interventions

Fernández Pena, A. and Viana Matesanz, M. and Rodríguez Vila, Borja and Oropesa García, Ignacio and Sánchez González, Patricia and Sánchez Margallo, Juan Antonio and Moyano García-Cuevas, J.L. and Sánchez Margallo, Francisco Miguel and Gómez Aguilera, Enrique J. (2015). Free-hand 3D reconstruction and tumor segmentation of Laparoscopic Ultrasounds for pancreatic MIS interventions. In: "Libro de Actas del XXXIII Congreso Anual de la Sociedad Española de Ingeniería Biomédica (CASEIB 2015)", 04/11/2015 - 06/11/2015, Madrid, Spain. ISBN 978-84-608-3354-3. pp. 71-74.

Description

Title: Free-hand 3D reconstruction and tumor segmentation of Laparoscopic Ultrasounds for pancreatic MIS interventions
Author/s:
  • Fernández Pena, A.
  • Viana Matesanz, M.
  • Rodríguez Vila, Borja
  • Oropesa García, Ignacio
  • Sánchez González, Patricia
  • Sánchez Margallo, Juan Antonio
  • Moyano García-Cuevas, J.L.
  • Sánchez Margallo, Francisco Miguel
  • Gómez Aguilera, Enrique J.
Item Type: Presentation at Congress or Conference (Article)
Event Title: Libro de Actas del XXXIII Congreso Anual de la Sociedad Española de Ingeniería Biomédica (CASEIB 2015)
Event Dates: 04/11/2015 - 06/11/2015
Event Location: Madrid, Spain
Title of Book: XXXIII Congreso Anual de la Sociedad Española de Ingeniería Biomédica (CASEIB 2015)
Date: 2015
ISBN: 978-84-608-3354-3
Subjects:
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Tecnología Fotónica y Bioingeniería
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img] PDF - Users in campus UPM only - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (245kB)

Abstract

Pancreatic cancer's treatment dilemma comes while trying to determine the precise nature of the lesion. The best approach is defined by diagnose of the tumor cells' staging. This paper presents a fast approach towards acquiring an estimation of the tumor positioning and size through laparoscopic ultrasound (LUS) images. The method segments 2D images of pancreas and lesions before reconstructing the extracted tumors into a full 3D volume. The whole method is integrated into a visualization and analysis specialized software (3D Slicer) as a module to provide users with a better experience. Reconstruction positioning is aided by a tracking system for the LUS probe which generates the images. In order to validate the method, an experiment using ex vivo porcine pancreas was conducted. We demonstrate the feasibility of the tracked LUS navigation approach for the delimitation of tumor structures allocated in the pancreas. Results show time constrains, while accuracy suffers in some stretches according to the image quality. Distinguishable structures are successfully depicted on the reconstruction. Time constrains for image segmentation are considerably reduced to nearly a second per image when the method is integrated into 3D Slicer as a module over a common laptop computer. Full reconstruction is achieved in 33 seconds. This proves the usefulness of the application in addition to being able to display both 2D segmentation and 3D reconstruction methods results.

More information

Item ID: 41782
DC Identifier: http://oa.upm.es/41782/
OAI Identifier: oai:oa.upm.es:41782
Deposited by: Memoria Investigacion
Deposited on: 03 Sep 2016 11:13
Last Modified: 03 Sep 2016 11:13
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM